Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    average statistics and likelihoods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obviamente
    0.44
     quedaron
    0.42
     asesor
    0.41
     যাচ্ছিল
    0.40
    khidmat
    0.40
     noved
    0.40
     manifestly
    0.39
    Obviously
    0.39
    orben
    0.39
    ectl
    0.39
    POSITIVE LOGITS
     reportedly
    0.73
     estimated
    0.68
     average
    0.66
     Americans
    0.66
     durchschnitt
    0.65
     worldwide
    0.64
     statistically
    0.64
     American
    0.60
     supposedly
    0.58
     নাকি
    0.57
    Act Density 0.028%

    No Known Activations